# zylos-ai/zylos-core

🐙 Give your AI a life — open-source agent infrastructure for team collaboration.

Repository: https://github.com/zylos-ai/zylos-core
Canonical: https://ross.abutalabs.com/products/zylos-core
Homepage: https://zylos.ai
Language: JavaScript
License: MIT
License Family: permissive
Topics: ai, ai-worker, own-your-data, personal-ai-assistant, self-evolving, team-collaboration
Last push: 2026-08-18T15:36:10+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 98, longevity 15
- inputs: {"age_days": 212, "days_push": 15, "days_rel": 15, "gap_med": 1.0, "n_releases_24m": 47}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1151, forks 128 (observed 2026-08-28T04:03:46.757384+00:00)

## What it is
Zylos is an open-source agent infrastructure that gives LLM-based AI assistants persistent memory, multi-channel communication (Telegram, Lark, Slack, WhatsApp, web console), and autonomous scheduling on your own server. It supports Claude Code and Codex as interchangeable runtimes, includes self-healing operations, and is compatible with the OpenClaw skill ecosystem.

## Use cases
- run an always-on AI assistant on my own server
- give my AI persistent memory across sessions
- connect my AI agent to Telegram and Slack
- schedule tasks for my AI to do while I sleep
- self-host a personal AI assistant that owns my data
- build an AI teammate that can extend its own skills
- switch between Claude and Codex runtimes without losing memory

## When to choose
- you want a self-hosted, privacy-focused AI agent with persistent memory and 24/7 availability
- you need one agent with unified memory across multiple messaging channels
- you want an agent that can schedule tasks and act autonomously
- you already have a Claude or Codex subscription and a Linux/Mac server

## When to avoid
- you need a simple stateless chatbot with no server infrastructure
- you want a managed cloud solution rather than self-hosting
- you don't have a Claude or OpenAI subscription to power the runtime
- you need a framework with a large established community and long track record

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, chatbot, scheduling, workflow-automation, chat-interface, self-hosted
- domain: large-language-models, chatbots, self-hosted, developer-tools
- platform: self-hosted, cli
- tags: persistent-memory, multi-channel-messaging, telegram, lark, claude-code, codex, openclaw-ecosystem, self-healing, autonomous-agent, own-your-data, ai-agents, automation, linux, macos, nodejs, web-server

## Member repositories
- zylos-ai/zylos-core (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:46.757384+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:33:38.216682+00:00, confidence not recorded.
  - readme: https://github.com/zylos-ai/zylos-core (fetched 2026-08-28T04:03:46.757384+00:00, sha ce389b6b558e)
  - homepage: https://zylos.ai (fetched 2026-08-29T12:38:39.507199+00:00, sha 7687136a6d8d)
  - site_page: https://zylos.ai/docs (fetched 2026-08-29T12:38:39.516078+00:00, sha afec6a55d03c)
- Data as of 2026-08-30T08:39:29.467469+00:00.